On Sat, Mar 22, 2014 at 06:01:18PM +0100, Frederic Weisbecker wrote: > 1) Call a per workqueue mutex when a work execute on an ordered workqueue. > Although > contention should be very rare (only while we replace the workqueue attrs > and > switch to a new worker), frequent locking may have a visible impact. > > 2) Have a seperate worker for all ordered workqueues. But we may lose a bit of > serialization with other workqueues along the way.
Ordered workqueues are always bound to the fallback default worker pool. Why not just adjust cpus_allowed of the worker pool? Thanks. -- tejun -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
